research-article

Open access

Exploring Interpretable AI Methods for ECG Data Classification

Authors:

Hårek Haugerud,

Pedro G. LindAuthors Info & Claims

ICDAR '24: Proceedings of the 5th ACM Workshop on Intelligent Cross-Data Analysis and Retrieval

Pages 11 - 18

https://doi.org/10.1145/3643488.3660294

Published: 11 June 2024 Publication History

All formats PDF

Abstract

We address ECG data classification, using methods from explainable artificial intelligence (XAI). In particular, we focus on the extended performance of the ST-CNN-5 model compared to established models. The model showcases slight improvement in accuracy suggesting the potential of this new model to provide more reliable predictions compared to other models. However, lower values of the specificity and area-under-curve metrics highlight the need to thoroughly evaluate the strengths and weaknesses of the extended model compared to other models. For the interpretability analysis, we use Shapley Additive Explanations (SHAP), Gradient-weighted Class Activation Mapping (GradCAM), and Local Interpretable Model-agnostic Explanations (LIME) methods. In particular, we show that the new model exhibits improved explainability in its GradCAM explanations compared to the former model. SHAP effectively highlights crucial ECG features, better than GradCAM and LIME. The latter methods exhibit inferior performance, particularly in capturing nuanced patterns associated with certain cardiac conditions. By using distinctive methods in the interpretability analysis, we provide a systematic discussion about which ECG features are better - or worse - uncovered by each method.

References

[1]

2022. New Artificial Intelligence Tool Detects Often Overlooked Heart Diseases. https://www.cedars-sinai.org/newsroom/new-artificial-intelligence-tool-detects-often-overlooked-heart-diseases/. [Online; accessed on 19-February-2023].

[2]

Amulya Agrawal, Aniket Chauhan, Manu Kumar Shetty, Mohit D Gupta, Anubha Gupta, 2022. ECG-iCOVIDNet: Interpretable AI model to identify changes in the ECG signals of post-COVID subjects. Computers in Biology and Medicine 146 (2022), 105540.

Digital Library

[3]

Keyvan Amini, Alireza Mirzaei, Mirtohid Hosseini, Hamed Zandian, Islam Azizpour, and Yagoob Haghi. 2022. Assessment of electrocardiogram interpretation competency among healthcare professionals and students of Ardabil University of Medical Sciences: a multidisciplinary study. BMC Medical Education 22, 1 (2022), 448.

[4]

Atul Anand, Tushar Kadian, Manu Kumar Shetty, and Anubha Gupta. 2022. Explainable AI decision model for ECG data of cardiac disorders. Biomedical Signal Processing and Control 75 (2022), 103584.

[5]

Zachi I Attia, Peter A Noseworthy, Francisco Lopez-Jimenez, Samuel J Asirvatham, Abhishek J Deshmukh, Bernard J Gersh, Rickey E Carter, Xiaoxi Yao, Alejandro A Rabinstein, Brad J Erickson, 2019. An artificial intelligence-enabled ECG algorithm for the identification of patients with atrial fibrillation during sinus rhythm: a retrospective analysis of outcome prediction. The Lancet 394, 10201 (2019), 861–867.

[6]

Abid Ali Awan. 2023. Introduction to t-SNE. https://www.datacamp.com/tutorial/introduction-t-sne

[7]

Federico Cabitza, Davide Ciucci, and Raffaele Rasoini. 2019. A giant with feet of clay: On the validity of the data that feed machine learning in medicine. In Organizing for the Digital World: IT for Individuals, Communities and Societies. Springer, 121–136.

[8]

Diogo V Carvalho, Eduardo M Pereira, and Jaime S Cardoso. 2019. Machine learning interpretability: A survey on methods and metrics. Electronics 8, 8 (2019), 832.

[9]

ECG Waves. n.d. Clinical ECG Interpretation. https://ecgwaves.com/course/the-ecg-book/

[10]

Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. MIT Press. http://www.deeplearningbook.org.

Digital Library

[11]

Tong He, Zhi Zhang, Hang Zhang, Zhongyue Zhang, Junyuan Xie, and Mu Li. 2019. Bag of tricks for image classification with convolutional neural networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 558–567.

[12]

Steven A Hicks, Jonas L Isaksen, Vajira Thambawita, Jonas Ghouse, Gustav Ahlberg, Allan Linneberg, Niels Grarup, Inga Strümke, Christina Ellervik, Morten Salling Olesen, 2021. Explaining deep neural networks for knowledge discovery in electrocardiogram analysis. Scientific reports 11, 1 (2021), 10949.

[13]

Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735–1780.

Digital Library

[14]

Jeremy Howard and Sylvain Gugger. 2020. Fastai: A layered API for deep learning. Information 11, 2 (2020), 108.

[15]

Md Islam, Md Haque, Hasib Iqbal, Md Hasan, Mahmudul Hasan, Muhammad Nomani Kabir, 2020. Breast cancer prediction: a comparative study using machine learning techniques. SN Computer Science 1, 5 (2020), 1–14.

Digital Library

[16]

Hassan Ismail Fawaz, Benjamin Lucas, Germain Forestier, Charlotte Pelletier, Daniel F Schmidt, Jonathan Weber, Geoffrey I Webb, Lhassane Idoumghar, Pierre-Alain Muller, and François Petitjean. 2020. Inceptiontime: Finding alexnet for time series classification. Data Mining and Knowledge Discovery 34, 6 (2020), 1936–1962.

Digital Library

[17]

Anthony H Kashou, Wei-Yin Ko, Zachi I Attia, Michal S Cohen, Paul A Friedman, and Peter A Noseworthy. 2020. A comprehensive artificial intelligence–enabled electrocardiogram interpretation program. Cardiovascular Digital Health Journal 1, 2 (2020), 62–70.

[18]

Shaan Khurshid, Samuel Friedman, Christopher Reeder, Paolo Di Achille, Nathaniel Diamant, Pulkit Singh, Lia X Harrington, Xin Wang, Mostafa A Al-Alusi, Gopal Sarma, 2022. ECG-based deep learning and clinical risk factors to predict atrial fibrillation. Circulation 145, 2 (2022), 122–133.

[19]

Yogesh Kumar, Apeksha Koul, Ruchi Singla, and Muhammad Fazal Ijaz. 2023. Artificial intelligence in disease diagnosis: a systematic literature review, synthesizing framework and future research agenda. Journal of ambient intelligence and humanized computing 14, 7 (2023), 8459–8486.

[20]

Hui Wen Loh, Chui Ping Ooi, Silvia Seoni, Prabal Datta Barua, Filippo Molinari, and U Rajendra Acharya. 2022. Application of explainable artificial intelligence for healthcare: A systematic review of the last decade (2011–2022). Computer Methods and Programs in Biomedicine (2022), 107161.

[21]

Francisco Lopez-Jimenez, Zachi Attia, Adelaide M Arruda-Olson, Rickey Carter, Panithaya Chareonthaitawee, Hayan Jouni, Suraj Kapa, Amir Lerman, Christina Luong, Jose R Medina-Inojosa, 2020. Artificial intelligence in cardiology: present and future. In Mayo Clinic Proceedings, Vol. 95. Elsevier, 1015–1039.

[22]

Gianluca Malato. 2021. How to explain neural networks using SHAP. https://towardsdatascience.com/how-to-explain-neural-networks-using-shap-2e8a0d688730

[23]

Sarang Narkhede. 2018. Understanding AUC - ROC Curve. https://towardsdatascience.com/understanding-auc-roc-curve-68b2303cc9c5

[24]

Ayush Pandey, Rakesh Chandra Joshi, and Malay Kishore Dutta. 2023. Automated Classification of Heart Disease using Deep Learning. In 2023 International Conference on Advancement in Computation & Computer Technologies (InCACCT). IEEE, 358–362.

[25]

Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019).

[26]

Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. "Why Should I Trust You?": Explaining the Predictions of Any Classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, August 13-17, 2016. 1135–1144.

Digital Library

[27]

Konstantinos C Siontis, Peter A Noseworthy, Zachi I Attia, and Paul A Friedman. 2021. Artificial intelligence-enhanced electrocardiography in cardiovascular disease management. Nature Reviews Cardiology 18, 7 (2021), 465–478.

[28]

Sulaiman Somani, Adam J Russak, Felix Richter, Shan Zhao, Akhil Vaid, Fayzan Chaudhry, Jessica K De Freitas, Nidhi Naik, Riccardo Miotto, Girish N Nadkarni, 2021. Deep learning and the electrocardiogram: review of the current state-of-the-art. EP Europace 23, 8 (2021), 1179–1191.

[29]

Mayo Clinic Staff. 2022. Electrocardiogram (ECG or EKG). [Online; accessed on 19-February-2023].

[30]

Nils Strodthoff, Patrick Wagner, Tobias Schaeffter, and Wojciech Samek. 2020. Deep learning for ECG analysis: Benchmarks and insights from PTB-XL. IEEE Journal of Biomedical and Health Informatics 25, 5 (2020), 1519–1528.

[31]

Kush R. Varshney. 2022. Trustworthy Machine Learning. Independently Published. http://trustworthymachinelearning.com/.

[32]

Neha Vishwakarma. 2023. Visualizing Model Insights: A Guide to Grad-CAM in Deep Learning. https://www.analyticsvidhya.com/blog/2023/12/grad-cam-in-deep-learning/

[33]

Patrick Wagner, Nils Strodthoff, Ralf-Dieter Bousseljot, Wojciech Samek, and Tobias Schaeffter. 2020. PTB-XL, a large publicly available electrocardiography dataset. https://doi.org/10.13026/qgmg-0d46

[34]

Zekai Wang, Stavros Stavrakis, and Bing Yao. 2023. Hierarchical deep learning with Generative Adversarial Network for automatic cardiac diagnosis from ECG signals. Computers in Biology and Medicine (2023), 106641.

[35]

Zhiguang Wang, Weizhong Yan, and Tim Oates. 2017. Time series classification from scratch with deep neural networks: A strong baseline. In 2017 International joint conference on neural networks (IJCNN). IEEE, 1578–1585.

[36]

Sergey Zagoruyko and Nikos Komodakis. 2016. Wide residual networks. arXiv preprint arXiv:1605.07146 (2016).

[37]

Yunfeng Zhang, Q Vera Liao, and Rachel KE Bellamy. 2020. Effect of confidence and explanation on accuracy and trust calibration in AI-assisted decision making. In Proceedings of the 2020 conference on fairness, accountability, and transparency. 295–305.

Digital Library

Cited By

Ding CYao TWu CNi J(2024)Advances in Deep Learning for Personalized ECG Diagnostics: A Systematic Review Addressing Inter-Patient Variability and Generalization ConstraintsBiosensors and Bioelectronics10.1016/j.bios.2024.117073(117073)Online publication date: Dec-2024
https://doi.org/10.1016/j.bios.2024.117073

Index Terms

Exploring Interpretable AI Methods for ECG Data Classification
1. Computing methodologies
  1. Artificial intelligence

Recommendations

Application of explainable artificial intelligence for healthcare: A systematic review of the last decade (2011–2022)
Highlights
- Examined studies that used the explainable artificial intelligence (XAI) technique for AI model in healthcare applications.
Abstract Background and objectives
Artificial intelligence (AI) has branched out to various applications in healthcare, such as health services management, predictive medicine, clinical decision-making, and patient data and ...
Explainable artificial intelligence, lawyer's perspective
ICAIL '21: Proceedings of the Eighteenth International Conference on Artificial Intelligence and Law

Explainable artificial intelligence (XAI) is a research direction that was already put under scrutiny, in particular in the AI&Law community. Whilst there were notable developments in the area of (general, not necessarily legal) XAI, user experience ...
Studying the explanations for the automated prediction of bug and non-bug issues using LIME and SHAP
AbstractContext
The identification of bugs within issues reported to an issue tracking system is crucial for triage. Machine learning models have shown promising results for this task. However, we have only limited knowledge of how such models identify ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

ICDAR '24: Proceedings of the 5th ACM Workshop on Intelligent Cross-Data Analysis and Retrieval

June 2024

48 pages

ISBN:9798400705496

DOI:10.1145/3643488

Copyright © 2024 Owner/Author.

This work is licensed under a Creative Commons Attribution International 4.0 License.

Sponsors

SIGMM: ACM Special Interest Group on Multimedia

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 11 June 2024

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Funding Sources

NordSTAR - OsloMet

Conference

ICMR '24

Sponsor:

SIGMM

ICMR '24: International Conference on Multimedia Retrieval

June 10 - 14, 2024

Phuket, Thailand

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
790
Total Downloads

Downloads (Last 12 months)790
Downloads (Last 6 weeks)130

Reflects downloads up to 08 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Ding CYao TWu CNi J(2024)Advances in Deep Learning for Personalized ECG Diagnostics: A Systematic Review Addressing Inter-Patient Variability and Generalization ConstraintsBiosensors and Bioelectronics10.1016/j.bios.2024.117073(117073)Online publication date: Dec-2024
https://doi.org/10.1016/j.bios.2024.117073

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Figures

Tables

Media

View Table of Conten